Neural image analysis in determining the content of dry matter in corn cob

The aim of this research was investigate the possibility of using methods of computer image analysis and neural modeling for assess the amount of dry matter in the tested corn cobs. The research lead to the conclusion that the neural image analysis may be a useful tool in determining the quantity of dry matter in this material. Generated neural models may be the beginning of research into the use of neural image analysis assess the content of dry matter in individual corn fractions. The presented models: RBF 31:31-20-1:1 characterized by RMS test error 0.244136 and RBF 18:22-1-1:1 characterized by RMS test error 0.230206 may be more efficient for more learning data. PiAO software and STATISTICA software were used in this work.